[Refactor] move deep_gemm_wrapper out of quantization (#11784)

2025-10-17 18:57:54 -07:00
parent 13219e1e48
commit 5b214b50b6
19 changed files with 18 additions and 24 deletions
--- a/python/sglang/srt/layers/quantization/fp8_utils.py
+++ b/python/sglang/srt/layers/quantization/fp8_utils.py
@@ -2,7 +2,7 @@ from typing import Callable, List, Optional, Tuple

 import torch

-from sglang.srt.layers.quantization import deep_gemm_wrapper
+from sglang.srt.layers import deep_gemm_wrapper
 from sglang.srt.layers.quantization.fp8_kernel import sglang_per_token_group_quant_fp8
 from sglang.srt.layers.quantization.mxfp4_tensor import MXFP4QuantizeUtil
 from sglang.srt.utils import is_sm100_supported, offloader